Study Protocol: Evaluation of AI-Driven Grading Compared to Manual Grading in Predicting Embryo Viability and Successful Implantation and Clinical Pregnancy Outcomes in IVF Using Static Microscopic Images

Journal of Pharmacy And Bioallied Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

A BSTRACT Background: Infertility affects 8–12% of couples globally, with 5–10% seeking Assisted Reproductive Technology (ART) annually. In-vitro fertilization (IVF) is the most common infertility treatment, involving retrieval oocytes and their in a laboratory setting. Embryo selection, crucial for IVF success, traditionally performed manually by embryologists using Gardner Scale. However, this process subject to variability. Time-lapse microscopy artificial intelligence (AI)-based methods are being explored improved embryo though AI’s full potential has not been realized across diverse clinical settings. Objectives: The primary objective study compare AI-based grading conventional manual predicting pregnancy outcomes. Methodology: This prospective will be conducted at an clinic Sawangi, Wardha, Maharashtra, 222 participants aged 23–40 years undergoing Intra-Cytoplasmic Sperm Injection (ICSI). Embryos on Day 5 (blastocyst stage) imaged graded Life Whisperer Genetics (LWG), tool, skilled ASEBIR criteria. success rate pregnancy, confirmed presence gestational sac, outcome. Expected Results: expected show increased predictive efficiency, rigor, consistency AI-driven embryos, providing more economical solution IVF. Study Implications: focuses enhancing selection which could potentially improve assessment Further research needed incorporate other embryonic developmental stages comprehensive evaluation process.

Language: Английский

---

Deep learning classification integrating embryo images with associated clinical information from ART cycles

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 21, 2025

Language: Английский

---

Making and selecting the best embryo in the laboratory

Fertility and Sterility, Journal Year: 2022, Volume and Issue: 120(3), P. 457 - 466

Published: Dec. 13, 2022

Language: Английский

---

Evaluation of the Clinical Efficacy and Trust in AI-Assisted Embryo Ranking: Survey-Based Prospective Study

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e52637 - e52637

Published: May 6, 2024

Background Current embryo assessment methods for in vitro fertilization depend on subjective morphological assessments. Recently, artificial intelligence (AI) has emerged as a promising tool assessment; however, its clinical efficacy and trustworthiness remain unproven. Simulation studies may provide additional evidence, provided that they are meticulously designed to mitigate bias variance. Objective The primary objective of this study was evaluate the benefits an AI model predicting pregnancy through well-designed simulations. secondary identify characteristics potential subgroups embryologists with varying degrees experience. Methods This simulation involved questionnaire-based survey conducted 61 levels experience from 12 clinics. via Google Forms (Google Inc) three phases: (1) phase 1, initial (December 23, 2022, January 22, 2023); (2) 2, validation (March 6, 2023, April 5, (3) 3 AI-guided 2023). Inter- intraobserver assessments accuracy selection 360 day-5 embryos before after guidance were analyzed all senior junior embryologists. Results With guidance, interobserver agreement increased 0.355 0.527 0.440 0.524 embryologists, respectively, thus reaching similar agreement. In test accurate 90 questions, numbers correct responses by only, only 34 (38%), 45 (50%), 59 (66%), respectively. Without AI, average score (accuracy) group 33.516 (37%), while 35.967 (40%), P<.001 t test. 46.581 (52%), level 44.833 P=.34. Junior had higher trust score. Conclusions demonstrates selecting high chances pregnancy, particularly 5 years or less experience, possibly due their AI. Thus, using auxiliary practice improve increase probability successful pregnancy.

Language: Английский

---

Making and Selecting the Best Embryo in In vitro Fertilization

Archives of Medical Research, Journal Year: 2024, Volume and Issue: 55(8), P. 103068 - 103068

Published: Aug. 26, 2024

Language: Английский

---

Application of artificial intelligence in gametes and embryos selection

Human Fertility, Journal Year: 2023, Volume and Issue: 26(4), P. 757 - 777

Published: Aug. 8, 2023

AbstractGamete and embryo quality are critical to the success rate of Assisted Reproductive Technology (ART) cycles, but there remains a lack methods accurately measure sperm, oocytes embryos. The ability Artificial Intelligence (AI) technology analyze large amounts data, especially video images, is particularly useful in gamete assessment selection. well-trained model has fast calculation speed high accuracy, which can help embryologists perform more objective Various artificial intelligence models have been developed for assessment, some exhibit good performance. In this review, we summarize latest applications AI semen analysis, as well selection oocyte embryo, discuss existing problems development directions field.Keywords: intelligencemachine learningembryo selectionoocyte selectionsperm selectionsemen analysis Disclosure statementNo potential conflict interest was reported by author(s).Data availability statementThe authors confirm that data supporting findings study available within article its supplementary materials.Additional informationFundingThis work supported National Key Research & Development Program China [2021YFC2700603].

Language: Английский

---

An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization

Scientific Data, Journal Year: 2023, Volume and Issue: 10(1)

Published: May 11, 2023

Abstract Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One key procedures in this treatment is selection and transfer embryo with highest developmental potential. To assess potential, clinical embryologists routinely work static images (morphological assessment) or short video sequences (time-lapse annotation). Recently, Artificial Intelligence models were utilized support procedure. Even though they have proven their great potential different vitro fertilization settings, there still considerable room for improvement. advancement algorithms research field, we built a dataset consisting blastocyst additional annotations. As such, Gardner criteria annotations, depicting morphological rating scheme, collected parameters are provided. The presented intended be used train deep learning on predict Gardner’s outcomes such as live birth. A benchmark human expert’s performance annotating

Language: Английский

---

Comparing performance between clinics of an embryo evaluation algorithm based on time-lapse images and machine learning

Journal of Assisted Reproduction and Genetics, Journal Year: 2023, Volume and Issue: 40(9), P. 2129 - 2137

Published: July 10, 2023

This article aims to assess how differences in maternal age distributions between IVF clinics affect the performance of an artificial intelligence model for embryo viability prediction and proposes a method account such differences.Using retrospectively collected data from 4805 fresh frozen single blastocyst transfers embryos incubated 5 6 days, discriminative was assessed based on fetal heartbeat outcomes. The 4 clinics, discrimination measured terms area under ROC curves (AUC) each clinic. To different age-standardizing AUCs developed which clinic-specific were standardized using weights according relative frequency relevant clinic compared distribution common reference population.There substantial variation with estimates ranging 0.58 0.69 before standardization. age-standardization reduced between-clinic variance by 16%. Most notably, three had quite similar after standardization, while last markedly lower AUC both without standardization.The that is proposed this mitigates some variability clinics. enables comparison where difference accounted for.

Language: Английский

---

Non-invasive prediction of human embryonic ploidy using artificial intelligence: a systematic review and meta-analysis

EClinicalMedicine, Journal Year: 2024, Volume and Issue: 77, P. 102897 - 102897

Published: Oct. 24, 2024

Language: Английский

---

Image Processing Approach for Grading IVF Blastocyst: A State-of-the-Art Review and Future Perspective of Deep Learning-Based Models

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(2), P. 1195 - 1195

Published: Jan. 16, 2023

The development of intelligence-based methods and application systems has expanded for the use quality blastocyst selection in vitro fertilization (IVF). Significant models on assisted reproductive technology (ART) have been discovered, including ones that process morphological image approaches extract attributes quality. In this study, (1) state-of-the-art ART is established using an automated deep learning approach, applications grading blastocysts IVF, related processing techniques. (2) Thirty final publications IVF were found by extensive literature search from databases several relevant sets keywords based papers published full-text English articles between 2012 2022. This scoping review sparks fresh thought learning-based grading. (3) introduces a novel notion realm utilizing applications, showing these can frequently match or even outperform skilled embryologists particular tasks. adds to our understanding procedure selecting embryos are suitable implantation offers important data creation computer-based system applies learning.

Language: Английский

---